jasonhuang3
/

Pro6000-bpo-qwen-2-5-7b-math-balance_logistic_alpha_0.3_lora_by_source_index_28k

Generated from Trainer

Model card Files Files and versions

Pro6000-bpo-qwen-2-5-7b-math-balance_logistic_alpha_0.3_lora_by_source_index_28k

177 MB

1 contributor

History: 15 commits

jasonhuang3's picture

Training in progress, step 7000

dcf6fe8 verified 28 days ago

.gitattributes

1.57 kB

Training in progress, step 500 29 days ago
adapter_config.json

932 Bytes

Training in progress, step 500 29 days ago
adapter_model.safetensors

162 MB
xet

Training in progress, step 7000 28 days ago
added_tokens.json

605 Bytes

Training in progress, step 500 29 days ago
chat_template.jinja

2.51 kB

Training in progress, step 500 29 days ago
merges.txt

1.67 MB

Training in progress, step 500 29 days ago
special_tokens_map.json

616 Bytes

Training in progress, step 500 29 days ago
tokenizer.json

11.4 MB
xet

Training in progress, step 500 29 days ago
tokenizer_config.json

4.69 kB

Training in progress, step 500 29 days ago
training_args.bin
Detected Pickle imports (11)
- "transformers.training_args.OptimizerNames",
- "accelerate.utils.dataclasses.DistributedType",
- "torch.device",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.SchedulerType",
- "trl.trainer.dpo_config.DPOConfig",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_utils.IntervalStrategy",
- "trl.trainer.dpo_config.FDivergenceType"
How to fix it?
6.93 kB
xet

Training in progress, step 500 29 days ago
vocab.json

2.78 MB

Training in progress, step 500 29 days ago